Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.
-
Upload
shawn-mckenzie -
Category
Documents
-
view
218 -
download
0
Transcript of Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.
![Page 1: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/1.jpg)
Interacting with a Musical Learning System: The Continuator
Presented by Ching-Hua Chuan
![Page 2: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/2.jpg)
Introduction• Real-time interactive musical instruments that
are able to produce stylistically consistent music.
• The system learns music styles automatically, and is seamlessly integrated in the playing mode of the musicians.
Bernard Lubat The Continuator and children
![Page 3: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/3.jpg)
Inside the Continuator• Automatic learning and generation
– Hierarchical Markov models– Improvement of classic Markov models
• Interactive musical instrument– Real-time generation (timing issues)– Biasing Markov generation– Control and high-level structure
![Page 4: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/4.jpg)
Possible Continuations variable-order Markov chain
• Sequence #1: {A B C D}• Sequence #2:{A B B C}• Ex #1: a subsequence {B} has two possible
continuations: C (from sequence #1) and B (from sequence #2)
• Ex #2: {A B} C (1) or B (2)• Ex #3:{B B C} D (1) (longest possible
subsequence.• Ex #4: {A} {B, B} (repeat all similar
continuations)
![Page 5: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/5.jpg)
Improvement of classic Markov models
• No continuation is found. • Less refined reduction function. (pitch region instead of pitch)
- Fig1: {PR1 PR1 PR2 PR3 PR5} - Fig2: {PR1 PR1 PR2} - Continuation = {PR3}, which is G in this case.
![Page 6: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/6.jpg)
A typical hierarchy of reduction functions
• 1- pitch * duration * velocity• 2 – small pitch region * velocity• 3 – small pitch regions• 4 – large pitch regions
where the numbering indicates the order in which the functions are to be considered in cases of failure in the matching process.
![Page 7: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/7.jpg)
Real-time Generation• John McLaughlin, a mean duration of 66
milliseconds per note. A good estimation of the maximum delay between two fast notes is about 50 milliseconds.
• Incoming note detection, phrase end detection, step-by-step generation
![Page 8: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/8.jpg)
Biasing Markov Generation• Weighting the notes according to how they
match the external input.
piano in notes nb
piano and top common notes nbpianopFitness ),(
S=1, we get a musical automaton insensitive to the musical context,S=0, we get a reactive system which generates the closest musical
elements to the external input it finds in the database.
Context)Fitness(x,*S)(1b(x)Markov_Pro*SProb(x)
![Page 9: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/9.jpg)
Control and High-Level Structure
• Parameters allow the musician to switch on or off basic functions such as the learning process or the continuation process.
• By default, the system stops playing when the user does, to avoid superposition of improvisations.
• Other parameters: the number of notes to be generated by the system, the tempo of the generated sequence…
![Page 10: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/10.jpg)
Experimentations
• Indistinguishability • Attachment• Subjective Impressions: the AHA effect
Claude Barthelemy
![Page 11: Interacting with a Musical Learning System: The Continuator Presented by Ching-Hua Chuan.](https://reader035.fdocuments.us/reader035/viewer/2022080923/5697bf871a28abf838c8886f/html5/thumbnails/11.jpg)
Demo
• It’s show time!